| Component | vLLM |
| Severity | high (CVSS 8.2) |
| CVSS vector | CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H |
| Published (NVD) | 2026-05-22 |
| Last modified | 2026-07-23 |
| Affected versions | docker_desktop >= 4.62.0, < 4.68.0 |
| Fixed in | 4.68.0 |
| Weakness | CWE-829 |
| CISA KEV | not listed |
NVD description
The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered. Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.
What to do
- Upgrade vLLM to
4.68.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...